This paper introduces a framework for certifying the reliability of stochastic oracles and derives bounds on the minimum expected token cost for reliable oracle certification.

This paper introduces witness complexity, a measure for the minimum running time of a string's near-shortest description on a universal Turing machine.

The paper provides the first machine-checked universal proof, using ring theory, that value-independence implies identical marginal distributions for arithmetic masking, thereby extending the verifica…

This paper studies distribution testing with respect to bounded classes of distinguishers, revealing connections between testable learning, verification of learning algorithms, and testing of structur…

The paper studies the resources required to batch verify Boolean functions and provides lower bounds on the witness-query tradeoff based on approximate degree.

This paper analyzes the computational complexity of verifying feedforward neural networks when their weights are restricted to finite-width arithmetic, finding that verification remains NP-complete fo…

The paper proves that platform-deterministic inference is a necessary and sufficient condition for trustworthy AI, establishing that AI trust fundamentally relies on consistent arithmetic.

The paper introduces partial multi-neuron relaxation, a novel verification technique that selectively computes tight linear bounds for a small subset of neurons to improve the efficiency and tightness…

The paper introduces a graded symbolic verification method that models cumulative side-channel leakage, demonstrating that protocols safe under traditional binary attacker models can fail when continu…

The paper proposes a federated formal verification architecture that treats verification as a polyglot proof system, successfully validating it on complex production subsystems like a Raft consensus m…

This paper measures the lower bound for the shortest program generating a sequence, proving a conservation law and providing a deterministic engine to recover generating programs for certain sequences…

The paper identifies a universal, statistically predictable distribution (Mandelbrot) governing LLM outputs, enabling a highly efficient, model-agnostic scoring primitive for provenance and quality as…

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…

This paper characterizes the label complexity of certifying small missed mass in an empirical pipeline and shows that auditing the excluded pool is minimax rate-optimal.

The paper proposes a trust-boundary architecture using Lean 4 to verify the deterministic structured computations surrounding LLM pipelines, providing verifiable certificates for high-stakes deploymen…

This paper introduces ShannonProver, an agentic framework that automates cryptographic proofs in EasyCrypt, allowing for scalable proof verification.